We present a modular toolkit to perform joint speaker diarization and speaker identification. The toolkit can leverage on multiple models and algorithms which are defined in a configuration file. Such flexibility allows our system to work properly in various conditions (e.g., multiple registered speakers' sets, acoustic conditions and languages) and across application domains (e.g. media monitoring, institutional, speech analytics). In this demonstration we show a practical use-case in which speaker-related information is used jointly with automatic speech recognition engines to generate speaker-attributed transcriptions. To achieve that, we employ a user-friendly web-based interface to process audio and video inputs with the chosen configuration.
@article{arxiv.2409.05750,
title = {A Toolkit for Joint Speaker Diarization and Identification with Application to Speaker-Attributed ASR},
author = {Giovanni Morrone and Enrico Zovato and Fabio Brugnara and Enrico Sartori and Leonardo Badino},
journal= {arXiv preprint arXiv:2409.05750},
year = {2024}
}
Comments
Show and Tell paper. Presented at Interspeech 2024